R Notebook

VADeaths

      Rural Male Rural Female Urban Male Urban Female
50-54       11.7          8.7       15.4          8.4
55-59       18.1         11.7       24.3         13.6
60-64       26.9         20.3       37.0         19.3
65-69       41.0         30.9       54.6         35.1
70-74       66.0         54.3       71.1         50.0

barplot(
  gd$`Rural Male`,
  horiz = T,
  col = "skyblue",
  border = "red",
  names.arg = c("50-54", "55-59", "60-64", "65-69", "70-74"),
  main = "Death Rate among Rural Male in Virginia",
  xlab = "Age Group",
  ylab = "Rate"
)

Stacked Bar diagram

legend("topright", legend = rownames(VADeaths))

Error in (function (s, units = "user", cex = NULL, font = NULL, vfont = NULL,  : 
  plot.new has not been called yet

Pie Chart

Pie Charts with Percentage

gd$piePercent <- round(100*gd$`Rural Male`/sum(gd$`Rural Male`))
pie(
  gd$`Rural Male`,
  labels = paste(gd$piePercent, "%"),
  main = "% Deaths by Age groups for Rural Male",
  col = rainbow(length(gd$`Rural Male`))
)
legend(
  "topright",
  c("50-54", "55-59", "60-64", "65-69", "70-74"),
  cex = 0.8,
  fill = rainbow(length(gd$`Rural Male`))
)

Air Passengers data

Histogram

gdcar <- as.data.frame(cars)
str(gdcar)

'data.frame':   50 obs. of  2 variables:
 $ speed: num  4 4 7 7 8 9 10 10 10 11 ...
 $ dist : num  2 10 4 22 16 10 18 26 34 17 ...

hist(gdcar$speed, col = "steelblue")

# add number of breaks
hist(gdcar$speed, col = "steelblue", breaks = 10)

dens <- density(cars$speed)
plot(dens, frame=FALSE, col="steelblue", main="Desnsity Plot of MPG")

Q-Q plot with Q-Q line

qqnorm(gdcar$speed)
qqline(gdcar$speed, col="red")

Scatterplot

• Speed = x-axis = independent variable

plot(gdcar$speed, gdcar$dist)

Boxplot: Easiest way to detect outliers

boxplot(mpg ~ cyl, data = mtcars)

boxplot(
  mpg ~ cyl,
  data = mtcars,
  xlab = "Number of cylinders",
  ylab = "Miles per Gallon",
  main = "Mileage Data"
)

qqnorm(mtcars$mpg)

# Normal Q-Q line
qqline(mtcars$mpg, col="red")

str(mtcars)

'data.frame':   32 obs. of  11 variables:
 $ mpg : num  21 21 22.8 21.4 18.7 18.1 14.3 24.4 22.8 19.2 ...
 $ cyl : num  6 6 4 6 8 6 8 4 4 6 ...
 $ disp: num  160 160 108 258 360 ...
 $ hp  : num  110 110 93 110 175 105 245 62 95 123 ...
 $ drat: num  3.9 3.9 3.85 3.08 3.15 2.76 3.21 3.69 3.92 3.92 ...
 $ wt  : num  2.62 2.88 2.32 3.21 3.44 ...
 $ qsec: num  16.5 17 18.6 19.4 17 ...
 $ vs  : num  0 0 1 1 0 1 0 1 1 1 ...
 $ am  : num  1 1 1 0 0 0 0 0 0 0 ...
 $ gear: num  4 4 4 3 3 3 3 4 4 4 ...
 $ carb: num  4 4 1 1 2 1 4 2 2 4 ...

df <- as.data.frame(mtcars)
f.cyl <- as.factor(df$cyl)

bpd <- table(df$cyl)

barplot(bpd)

l

[1] 5

Histogram and abline for mean of “mpg”

hist(df$mpg, col="steelblue", main="Histogram of MPG", xlab="MPG Categories")
abline(v=mean(df$mpg), lwd=3, lty=2)

qqnorm(mtcars$mpg)
qqline(mtcars$mpg, col="red")

hist(df$mpg, col="steelblue", main="Histogram of MPG", xlab="MPG Categories")
abline(v=mode(df$mpg), lwd=3, lty=2)

Warning: NAs introduced by coercion

mode_value <- as.numeric(names(sort(table(df), decreasing = TRUE)[1]))

Error in table(df) : attempt to make a table with >= 2^31 elements

Correlation

• linear - Pearson correlation cofficient
• non-linear - Spearman Rank correlation cofficient